13 papers
CoDA: Co-Evolution of Data Engines and Action Policies
Tianjiao Yu, Zhilin Ou, Yifan Shen +5
Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environme…
OpenDepth: Repurposing Image Editing Priors for Robust Open-World Monocular Depth Estimation
Mengke Zhang, Tianyi Yang, Xinzhuo Li +1
Recently, the integration of generative priors has revolutionized Monocular Depth Estimation (MDE), achieving state-of-the-art (SOTA) performance with remarkably high data efficien…
GaussianSeed: Hierarchical Gaussian Seeding for High-Resolution 3D Occupancy Prediction
Xinzhuo Li, Xianghui Pan, Jiayuan Du +4
Vision-centric 3D occupancy prediction provides dense scene representations essential for autonomous driving and robotic navigation, yet existing methods struggle to scale to high…
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
Tianjiao Yu, Xinzhuo Li, Yifan Shen +4
Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit. Existi…
CogniRoute: Learning to Route Social Evidence in Omni-Modal Models
Yifan Shen, Pei Tian, Xinzhuo Li +8
Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially prono…
VTAM: Efficient Visuo-Tactile World-Action Models for Contact-Rich Manipulation without Tactile Pretraining
Haoran Yuan, Weigang Yi, Zhenyu Zhang +11
Tactile vision-language-action models (VLAs) and tactile world-action models (WAMs) are a promising new paradigm for contact-rich manipulation, but existing models either underutil…
EgoForge: Goal-Directed Egocentric World Simulator
Yifan Shen, Jiateng Liu, Xinzhuo Li +9
Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object intera…
DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
Tianjiao Yu, Xinzhuo Li, Muntasir Wahed +4
Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic…
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
Haochang Hao, Yifan Xu, Xinzhuo Li +2
Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which rec…
Toward Cognitive Supersensing in Multimodal Large Language Model
Boyi Li, Yifan Shen, Yuanzhe Liu +12
Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited…
CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence
Tianjiao Yu, Xinzhuo Li, Yifan Shen +2
Recent advances in large multimodal models suggest that explicit reasoning mechanisms play a critical role in improving model reliability, interpretability, and cross-modal alignme…
Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination
Xinzhuo Li, Adheesh Juvekar, Jiaxun Zhang +6
Segmentation Vision-Language Models (VLMs) have significantly advanced grounded visual understanding, yet they remain prone to pixel-grounding hallucinations, producing masks for i…
PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
Muntasir Wahed, Kiet A. Nguyen, Adheesh Sunil Juvekar +6
Despite significant advancements in Large Vision-Language Models (LVLMs)' capabilities, existing pixel-grounding models operate in single-image settings, limiting their ability to…